Concordance with evidence-based medicine (EBM) guidelines is associated with improved clinical outcomes in spine surgery. The North American Spine Society (NASS) has published coverage guidelines on indications for lumbar fusion surgery, with a recent survey demonstrating a 60% concordance rate across its members. GPT-4 is a popular deep learning model that receives knowledge training across public databases including those containing EBM guidelines. There is prior research exploring the potential utility of artificial intelligence (AI) software in adherence with spine surgery practices and guidelines, inviting opportunity to further investigate application in the setting of lumbar fusion surgery with current AI models. Seventeen well-validated clinical vignettes with specific indications for or against lumbar fusion based on NASS criteria were obtained from a prior published research study. Each case was transcribed into a standardized prompt and entered into GPT-4 to obtain a decision whether fusion is indicated. Interquery reliability was assessed with serial identical queries utilizing the Fleiss' Kappa statistic. Majority response among serial queries was considered as the final GPT-4 decision. Queries were all entered in separate strings. The investigator entering the prompts was blinded to the NASS-concordant decisions for the cases prior to complete data collection. Decisions by GPT-4 and NASS guidelines were compared with Chi-square analysis. GPT-4 responses for 15/17 (88.2%) of the clinical vignettes were in concordance with NASS EBM lumbar fusion guidelines. There was a significant association in clinical decision-making when determining indication for spine fusion surgery between GPT-4 and NASS guidelines (χ² = 9.75; p<.01). There was substantial agreement among the sets of responses generated by GPT-4 for each clinical case (K = 0.71; p<.001). There is significant concordance between GPT-4 responses and NASS EBM indications for lumbar fusion surgery. AI and deep learning models may prove to be an effective adjunct tool for clinical decision-making within modern spine surgery practices.
Purpose: Traumatic dental injuries (TDIs) are a significant public health concern, particularly in rural areas where limited access to dental care and unique risk factors contribute to injury prevalence. This study analyzed the epidemiology of pediatric TDIs in rural Central Pennsylvania over a nine-year period to identify common TDI types and etiologies, examine demographic and seasonal trends, explore gender differences, and inform preventive strategies to improve emergency dental care access. Methods: A retrospective review of electronic health records from 268 pediatric patients (ages 6 months to 17 years) who presented with TDIs at Geisinger Medical Center’s emergency department between July 2010 and July 2019 was conducted. Variables including age, gender, injury etiology, season, and diagnosis were analyzed using descriptive statistics and chi-square tests (p < 0.05). Results: Of the 268 patients, 171 were male (63.8%), with a mean age of 11.9 years. A total of 350 orofacial injuries were recorded, with uncomplicated crown fractures (25.7%) and avulsions (18.6%) being most common. Males were more affected, particularly in summer (41.8%), with falls (21.9%) and sports-related activities (20.0%) as leading causes. The most frequently injured teeth were #E (20.4%) in primary dentition and #9 (38.6%) in permanent dentition. Conclusions: This study highlights the multifactorial nature of pediatric TDIs in rural settings, emphasizing the need for targeted preventive measures, especially among male adolescents. Key recommendations include promoting the use of protective gear during high-risk activities, enforcing safety regulations for recreational equipment, and improving access to emergency dental care.
Background: The use of artificial intelligence (AI) in medicine is rapidly evolving. However, its role in plastic and reconstructive surgery remains underexplored. Plastic surgery requires nuanced, dynamic decision making, and individualized care, making AI integration challenging. This study evaluates GPT-4's ability to respond to American Board of Plastic Surgery (ABPS) Oral Board-style clinical vignettes and assesses its potential as a decision making and educational adjunct. Methods: Twelve clinical vignettes spanning aesthetic, reconstructive, hand, craniofacial, pediatric, and trauma surgery were input into GPT-4. Each response was scored by 2 board-certified plastic surgeons across 6 clinical domains: Case Introduction, Diagnosis, Treatment Planning, Patient Counseling, Operative Steps, and Complication Management. Domains were scored on a 0–4 scale; scores <2 were considered failing. Interrater reliability was assessed via weighted κ . A structured qualitative interview was conducted. Results: GPT-4 achieved mean domain scores ranging from 2.3 to 3.7 across vignettes, with passing rates of 91.7% (rater 1) and 83.3% (rater 2). The highest-performing domains were Diagnosis (84.4%) and Complication Handling (82.3%), and the lowest-performing domains were seen in Case Introductions (62.5%). Interrater agreement was strong across domains ( κ = 0.70–0.89). Qualitative findings emphasized GPT-4's accuracy in guideline-based cases, limitations in trauma triage, and potential as an educational resource. Conclusion: GPT-4 demonstrates concordance with board-level clinical reasoning in structured plastic surgery scenarios. However, limitations in heuristic judgment and real-time adaptability underscore the need for optimization with specialty-specific training datasets and performance rubrics. With appropriate curation, GPT-4 could serve as a valuable supplement in surgical education and oral board preparation.
Retrospective cohort study. To determine whether patient-reported allergies (PRAs) are associated with pain, mobility, and functional outcomes following lumbar interbody fusion (LIF). Prior studies suggest PRAs may correlate with worse postoperative pain, disability, and satisfaction; however, findings are inconsistent, and their impact on LIF outcomes remains unclear. We retrospectively analyzed 325 adults undergoing elective LIF for degenerative pathology (November 2019-January 2023). Patients were stratified into ≥1 PRA (n=242) and no known allergies (n=83). Demographics, psychiatric history, preoperative opioid use, and allergy type were recorded. Primary outcomes included changes in Patient-reported outcome measures (PROMs; PROMIS overall, physical, and mental health) and Oswestry Disability Index (ODI) from baseline to 1 year. Secondary outcomes included Visual Analog Scale (VAS) and Activity Measure for Post-Acute Care (AMPAC) mobility. Multivariate regression assessed associations with outcomes. Minimal clinically important difference (MCID) thresholds were ODI ≥10 and PROMIS ≥8. Receiver operating characteristic analysis evaluated PRA count as a predictor of MCID. Patients with PRAs were more frequently female (57%; p=0.002) and had higher rates of psychiatric comorbidities (p=0.02). The PRA group demonstrated greater improvement in PROMIS overall (p=0.049) and mental health (p=0.026) scores, with no difference in ODI change. PRA count was not associated with VAS, AMPAC, or MCID attainment. Psychiatric history independently predicted lower odds of achieving MCID for PROMIS physical (odds ratio [OR], 0.52; p=0.048) and ODI (OR, 0.27; p=0.002). PRA count showed poor predictive value for MCID (area under the curve<0.600). PRAs were not associated with worse outcomes after LIF and were linked to greater improvement in PROMIS scores. Psychiatric history, but not allergy count, was a strong predictor of reduced MCID attainment.